import pandas as pd
from sklearn.model_selection import train_test_split
import joblib
import numpy as np
from sklearn.feature_selection import VarianceThreshold, SelectKBest, f_classif

# Show all columns in the DataFrame
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)

df = pd.read_csv('results/combined/Bagged_Ensemble_predictions.csv')

df.head()

	Protocol	Flow Duration	Tot Fwd Pkts	Tot Bwd Pkts	TotLen Fwd Pkts	TotLen Bwd Pkts	Fwd Pkt Len Max	Fwd Pkt Len Min	Fwd Pkt Len Mean	Fwd Pkt Len Std	Bwd Pkt Len Max	Bwd Pkt Len Min	Bwd Pkt Len Mean	Bwd Pkt Len Std	Flow Byts/s	Flow Pkts/s	Flow IAT Mean	Flow IAT Std	Flow IAT Max	Flow IAT Min	Fwd IAT Tot	Fwd IAT Mean	Fwd IAT Std	Fwd IAT Max	Fwd IAT Min	Bwd IAT Tot	Bwd IAT Mean	Bwd IAT Std	Bwd IAT Max	Bwd IAT Min	Fwd PSH Flags	Bwd PSH Flags	Fwd URG Flags	Bwd URG Flags	Fwd Header Len	Bwd Header Len	Fwd Pkts/s	Bwd Pkts/s	Pkt Len Min	Pkt Len Max	Pkt Len Mean	Pkt Len Std	Pkt Len Var	FIN Flag Cnt	SYN Flag Cnt	RST Flag Cnt	PSH Flag Cnt	ACK Flag Cnt	URG Flag Cnt	CWE Flag Count	ECE Flag Cnt	Down/Up Ratio	Pkt Size Avg	Fwd Seg Size Avg	Bwd Seg Size Avg	Fwd Byts/b Avg	Fwd Pkts/b Avg	Fwd Blk Rate Avg	Bwd Byts/b Avg	Bwd Pkts/b Avg	Bwd Blk Rate Avg	Subflow Fwd Pkts	Subflow Fwd Byts	Subflow Bwd Pkts	Subflow Bwd Byts	Init Fwd Win Byts	Init Bwd Win Byts	Fwd Act Data Pkts	Fwd Seg Size Min	Active Mean	Active Std	Active Max	Active Min	Idle Mean	Idle Std	Idle Max	Idle Min	cm_label
0	6.0	12.0	0.0	2.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	166666.670	12.0	0.0	12.0	12.0	0.0	0.0	0.0	0.0	0.0	12.0	12.0	0.0	12.0	12.0	0.0	0.0	0.0	0.0	0.0	64.0	0.0	166666.670	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2.0	0.0	-1.0	83.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	TN
1	6.0	12.0	0.0	2.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	166666.670	12.0	0.0	12.0	12.0	0.0	0.0	0.0	0.0	0.0	12.0	12.0	0.0	12.0	12.0	0.0	0.0	0.0	0.0	0.0	64.0	0.0	166666.670	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2.0	0.0	-1.0	83.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	TN
2	6.0	9.0	0.0	2.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	222222.220	9.0	0.0	9.0	9.0	0.0	0.0	0.0	0.0	0.0	9.0	9.0	0.0	9.0	9.0	0.0	0.0	0.0	0.0	0.0	64.0	0.0	222222.220	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2.0	0.0	-1.0	83.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	TN
3	6.0	29.0	0.0	2.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	68965.516	29.0	0.0	29.0	29.0	0.0	0.0	0.0	0.0	0.0	29.0	29.0	0.0	29.0	29.0	0.0	0.0	0.0	0.0	0.0	64.0	0.0	68965.516	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2.0	0.0	-1.0	83.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	TN
4	6.0	50.0	0.0	2.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	40000.000	50.0	0.0	50.0	50.0	0.0	0.0	0.0	0.0	0.0	50.0	50.0	0.0	50.0	50.0	0.0	0.0	0.0	0.0	0.0	64.0	0.0	40000.000	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2.0	0.0	-1.0	83.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	TP

# Tạo từ điển ánh xạ từ cm_label sang tên dễ hiểu hơn
label_mapping = {
    'TP': 'Phát hiện đúng MITM',
    'TN': 'Phát hiện đúng bình thường',
    'FP': 'Báo nhầm là MITM',
    'FN': 'Bỏ sót tấn công'
}

# Áp dụng thay thế
df['cm_label'] = df['cm_label'].replace(label_mapping)

label_counts = df['cm_label'].value_counts()
label_percent = df['cm_label'].value_counts(normalize=True) * 100
result = pd.DataFrame({'Count': label_counts, 'Percentage (%)': label_percent.round(2)})
print(result)

                            Count  Percentage (%)
cm_label                                         
Phát hiện đúng bình thường  24611           88.57
Phát hiện đúng MITM          2310            8.31
Bỏ sót tấn công               807            2.90
Báo nhầm là MITM               58            0.21

import seaborn as sns
import matplotlib.pyplot as plt

for col in df.select_dtypes(include='number').columns:
    plt.figure(figsize=(12, 4))
    sns.boxplot(y='cm_label', x=col, data=df)
    plt.title(f'Boxplot of {col} by Label')
    plt.show()

for col in df.select_dtypes(include='number').columns:
    plt.figure(figsize=(12, 4))
    sns.violinplot(y='cm_label', x=col, data=df)
    plt.title(f'Violin plot of {col} by Label')
    plt.show()